Zovo Currency Converter

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations, the description discloses the data source (European Central Bank euro reference rates), publication timing, rate type (indicative mid-market, not bank/card), return fields, and the 10-target-currency limit. The annotations already establish read-only and idempotent behavior, and the description adds meaningful operational context without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with usage guidance and remains reasonably compact. There is minor redundancy around cryptocurrency being unavailable, which slightly weakens conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple operation, full schema coverage, annotations, and an output schema, the description is largely complete: it covers source, timing, rate type, scope, and exclusions. The only notable contextual gap is that it does not explain how this tool relates to the sibling rate_history tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the input schema already documents amount, from, to, and date in detail. The description reinforces the date floor and 10-target limit but adds little parameter semantics beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: currency conversion and exchange-rate lookup, with examples such as USD to EUR and a date-based rate back to 1999-01-04. It is clear what the tool does, but it does not explicitly distinguish the tool from the sibling rate_history tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear when-to-use guidance for currency conversion and today's exchange rate, and explicit exclusions for crypto, metals, and live market quotes. The main gap is that it does not name rate_history or explain when to choose that sibling instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which already declare readOnly/idempotent/openWorld), it discloses the data source (ECB), the working-days-only behavior with no weekends or ECB holidays, hard limits of 5 currencies and 366 days, and the returned metrics plus CSV and line-chart artifacts. The 'not financial advice' caveat is also useful framing for an agent paraphrasing results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger sentence, then limits, then behavior, then exclusions — a sensible order with no filler. The return-format sentence runs long and partly duplicates the output schema, which keeps it below a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-required-param read tool with a full output schema and rich annotations, the description covers everything an agent needs: when to call it, data source, coverage limits, holiday behavior, and what comes back. No material gap remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema already documents formats and examples for base, quote, start and end. The description reinforces the 5-currency and 366-day caps and adds the ECB-source meaning, but contributes no new syntax or per-parameter detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('exchange rate history', 'historical exchange rate ... over a date range') and pins the data source to ECB euro reference rates. It never names the sibling convert_currency, so the boundary with that tool is only implied rather than stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It opens with an explicit trigger ('Use this when the user asks for...') covering several phrasings, and adds a clear exclusion: 'Do not use for stocks, crypto or commodity prices.' What's missing is a positive pointer to convert_currency for single-point conversions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.